Learning-Based Near-Orthogonal Superposition Code for MIMO Short Message Transmission

TL;DR

This paper introduces a deep learning-based near-orthogonal superposition coding scheme for MIMO channels, significantly improving short message transmission reliability in mMTC applications through end-to-end training and a novel decoding algorithm.

Contribution

It proposes a novel neural network-based encoding and decoding scheme for MIMO short messages, outperforming traditional methods with a new superposition coding approach.

Findings

Outperforms ML detection with polar codes by 1-2 dB in simulations.

Uses end-to-end learning for encoder and decoder optimization.

Introduces a looped K-best tree-search algorithm with CRC for decoding.

Abstract

Massive machine type communication (mMTC) has attracted new coding schemes optimized for reliable short message transmission. In this paper, a novel deep learning-based near-orthogonal superposition (NOS) coding scheme is proposed to transmit short messages in multiple-input multiple-output (MIMO) channels for mMTC applications. In the proposed MIMO-NOS scheme, a neural network-based encoder is optimized via end-to-end learning with a corresponding neural network-based detector/decoder in a superposition-based auto-encoder framework including a MIMO channel. The proposed MIMO-NOS encoder spreads the information bits to multiple near-orthogonal high dimensional vectors to be combined (superimposed) into a single vector and reshaped for the space-time transmission. For the receiver, we propose a novel looped K-best tree-search algorithm with cyclic redundancy check (CRC) assistance to enhance the error correcting ability in the block-fading MIMO channel. Simulation results show the proposed MIMO-NOS scheme outperforms maximum likelihood (ML) MIMO detection combined with a polar code with CRC-assisted list decoding by 1-2 dB in various MIMO systems for short (32-64 bit) message transmission.